PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

TL;DR

PanoGRF introduces a novel spherical radiance field approach that effectively synthesizes views from wide-baseline panoramas by leveraging 360-degree scene priors and monocular depth, outperforming existing methods.

Contribution

The paper presents PanoGRF, a new method that directly models spherical radiance fields for wide-baseline panoramas, avoiding panorama-to-perspective conversion and integrating depth priors for better geometry understanding.

Findings

PanoGRF outperforms state-of-the-art methods on multiple panoramic datasets.

It effectively synthesizes novel views from sparse, wide-baseline panoramic images.

The approach improves geometry accuracy using 360° monocular depth priors.

Abstract

Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these applications to reduce network bandwidth and storage requirements. However, synthesizing novel views from these panoramas remains a key challenge. Although existing neural radiance field methods can produce photorealistic views under narrow-baseline and dense image captures, they tend to overfit the training views when dealing with \emph{wide-baseline} panoramas due to the difficulty in learning accurate geometry from sparse $360^{\circ}$ views. To address this problem, we propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas, which construct spherical radiance fields incorporating $360^{\circ}$ scene priors. Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection. Moreover, as some regions of the panorama are only visible from one view while invisible from others under wide baseline settings, PanoGRF incorporates $360^{\circ}$ monocular depth priors into spherical depth estimation to improve the geometry features. Experimental results on multiple panoramic datasets demonstrate that PanoGRF significantly outperforms state-of-the-art generalizable view synthesis methods for wide-baseline panoramas (e.g., OmniSyn) and perspective images (e.g., IBRNet, NeuRay).